Octavia I. Camps

Wavelets and electromagnetic power system transients

The wavelet transform is introduced as a method for analyzing electromagnetic transients associated with power system faults and switching. This method, like the Fourier transform, provides information related to the frequency composition of a waveform, but it is more appropriate than the familiar Fourier methods for the nonperiodic, wide-band signals associated with electromagnetic transients. It appears that the frequency domain data produced by the wavelet transform may be useful for analyzing the sources of transients through manual or automated feature detection schemes. The basic principles of wavelet analysis are set forth, and examples showing the application of the wavelet transform to actual power system transients are presented.

Detection of obstacles in the flight path of an aircraft

The National Aeronautics and Space Administration (NASA), along with members of the aircraft industry, recently developed technologies for a new supersonic aircraft. One of the technological areas considered for this aircraft is the use of video cameras and image-processing equipment to aid the pilot in detecting other aircraft in the sky. The detection techniques should provide high detection probability for obstacles that can vary from subpixel to a few pixels in size, while maintaining a low false alarm probability in the presence of noise and severe background clutter. Furthermore, the detection algorithms must be able to report such obstacles in a timely fashion, imposing severe constraints on their execution time. Approaches are described here to detect airborne obstacles on collision course and crossing trajectories in video images captured from an airborne aircraft. In both cases the approaches consist of an image-processing stage to identify possible obstacles followed by a tracking stage to distinguish between true obstacles and image clutter, based on their behavior. For collision course object detection, the image-processing stage uses morphological filter to remove large-sized clutter. To remove the remaining small-sized clutter, differences in the behavior of image translation and expansion of the corresponding features is used in the tracking stage. For crossing object detection, the image-processing stage uses low-stop filter and image differencing to separate stationary background clutter. The remaining clutter is removed in the tracking stage by assuming that the genuine object has a large signal strength, as well as a significant and consistent motion over a number of frames. The crossing object detection algorithm was implemented on a pipelined architecture from DataCube and runs in real time. Both algorithms have been successfully tested on flight tests conducted by NASA.

Object recognition using appearance-based parts and relations

The recognition of general three-dimensional objects in cluttered scenes is a challenging problem. In particular, the design of a good representation suitable to model large numbers of generic objects that is also robust to occlusion has been a stumbling block in achieving success. In this paper, we propose a representation using appearance-based parts and relations to overcome these problems. Appearance-based parts and relations are defined in terms of closed regions and the union of these regions, respectively. The regions are segmented using the MDL principle, and their appearance is obtained from collection of images and compactly represented by parametric manifolds in the two eigenspaces spanned by the parts and the relations.

Dynamic Appearance Modeling for Human Tracking

Dynamic appearance is one of the most important cues for tracking and identifying moving people. However, direct modeling spatio-temporal variations of such appearance is often a difficult problem due to their high dimensionality and nonlinearities. In this paper we present a human tracking system that uses a dynamic appearance and motion modeling framework based on the use of robust system dynamics identification and nonlinear dimensionality reduction techniques. The proposed system learns dynamic appearance and motion models from a small set of initial frames and does not require prior knowledge such as gender or type of activity. The advantages of the proposed tracking system are illustrated with several examples where the learned dynamics accurately predict the location and appearance of the targets in future frames, preventing tracking failures due to model drifting, target occlusion and scene clutter.

Line-based recognition using a multidimensional Hausdorff distance

A line-feature-based approach for model based recognition using a four-dimensional Hausdorff distance is proposed. This approach reduces the problem of finding the rotation, scaling, and translation transformations between a model and an image to the problem of finding a single translation minimizing the Hausdorff distance between two sets of points in a four-dimensional space. The implementation of the proposed algorithm can be naturally extended to higher dimensional spaces to efficiently find correspondences between n-dimensional patterns. The method performance and sensitivity to segmentation problems are quantitatively characterized using an experimental protocol with simulated data. It is shown that the algorithm performs well, is robust to occlusion and outliers, and that it degrades nicely as the segmentation problems increase. Experiments with real images are also presented.

Wavelets and power system transients : feature detection and classification

This paper presents a methodology for the development of software for classifying power system disturbances by type from the transient waveform signature. The implementation of classification capability in future transient recorders will enable such features as selective storage of transient data (to better utilize limited storage media) and automated reporting of disturbances to central control facilities. The wavelet transform provides an effective and efficient means of decomposing voltage and current signals of power system transients to detectable and discriminant features. Similarities of power system transients to wide-band signals in other domains, the simultaneous presence of a resonant frequency, its harmonics, and impulse (high-frequency, time-localized) components, make this technique extendible to other classification systems. The classification algorithm uses statistical pattern recognition on features derived from the extreme representation of the transient waveform after processing the transient waveform by a non-orthogonal, quadratic spline wavelet. Training and classification testing use simulated waveforms of a 200 mile, three-phase transmission line produced by the Electromagnetic Transients Program (EMTP). A simple Bayesian classifier identifies an unknown transient waveform as a capacitor switching or fault transient, and locates the point of disturbance from one of two possible locations on the transmission line. Due to the effectiveness of the wavelet transform preprocessing, the classification system currently performs at 100 percent accuracy on four transient classes.

Hierarchical organization of appearance-based parts and relations for object recognition

Previously a new object representation using appearance-based parts and relations to recognize 3D objects from 2D images, in the presence of occlusion and background clutter, was introduced. Appearance-based parts and relations are defined in terms of closed regions and the union of these regions, respectively. The regions are segmented using the MDL principle, and their appearance is obtained from collection of images and compactly represented by parametric manifolds in the eigenspaces spanned by the parts and the relations. In this paper we introduce the discriminatory power of the proposed features and describe how to use it to organize large databases of objects.

Finite horizon model reduction of a class of neutrally stable systems with applications to texture synthesis and recognition

In this paper we address the problem of finite-horizon model reduction for a class of neutrally stable discrete-time systems. The main result of the paper shows that this problem can be solved by considering suitable defined Hankel operators and Grammians, leading to an algorithm similar to the well known balanced truncation. However, in this case the structure of the problem can be exploited to obtain tighter truncation error bounds. These results are illustrated with a non-trivial practical example arising in the context of image processing: texture synthesis and recognition.

Activity Recognition from Silhouettes using Linear Systems and Model (In)validation Techniques

In this work we propose a model (invalidation approach to gait recognition, using a system that tries to discriminate specific activities of people. The recognition process departs from an abstraction obtained from video image sequences for different activities performed by different people, by first using a suitable representation for each frame and for each frame sequence. For each frame two commonly used models for describing silhouettes are employed: Fourier descriptors and vectors of widths. Then each sequence is modeled as a linear time invariant (LTI) system that captures the dynamics of the evolution of the frame description vectors in time. Finally a standard classification tool, SVM, is used to recognize activities using similarity measures obtained through model (in)validation. The main contribution of this work is the provision of an activity recognition model and the performance evaluation of this model using two different feature spaces

Real-time obstacle detection system for high speed civil transport supersonic aircraft

The High Speed Civil Transport (HSCT) supersonic commercial aircraft under development by National Aeronautics and Space Administration (NASA) and its partners is expected to include an eXternal Visibility System (XVS) to aid the pilots limited view through their cockpit windows. XVS obtains video images using high resolution digital cameras mounted on the aircraft and directed outside the aircraft. The images captured by the XVS provide an opportunity for automatic computer analysis in real-time to alert pilots of potential hazards in the flight path. The system is useful to help pilots make decisions and avoid air collision. In this paper, we describe the design, implementation, and evaluation of such a computer vision system. Using this system, real-time image data was recently obtained successfully from night tests conducted at NASA Langley Research Center. The system successfully detected and tracked translating objects in real-time during the night test. The system is described in detail so that other researchers can easily replicate the work.